Hugging Face's logo

havinash-ai
/
377d8250-51d3-4829-b83f-26d1ea9dfb50

PEFT
Safetensors
phi3
axolotl
Generated from Trainer
custom_code
Model card Files
xet
 Community
377d8250-51d3-4829-b83f-26d1ea9dfb50
File size: 3,194 Bytes
f7f8f8b
 
 
8668f09
f7f8f8b
8668f09
f7f8f8b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9ae2d5c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b92edaf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8668f09
 
 
 
 
 
 
f7f8f8b
 
 
 
 
 
 
 
 
 
 
 
 
 
8668f09
f7f8f8b
 
 
 
8668f09
f7f8f8b
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007665772326561901,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007665772326561902,
      "grad_norm": 2.21907639503479,
      "learning_rate": 2e-05,
      "loss": 3.9583,
      "step": 1
    },
    {
      "epoch": 0.0007665772326561902,
      "eval_loss": 0.9905641674995422,
      "eval_runtime": 16.517,
      "eval_samples_per_second": 33.299,
      "eval_steps_per_second": 16.65,
      "step": 1
    },
    {
      "epoch": 0.0015331544653123803,
      "grad_norm": 1.9840973615646362,
      "learning_rate": 4e-05,
      "loss": 3.9198,
      "step": 2
    },
    {
      "epoch": 0.0022997316979685703,
      "grad_norm": 2.0610175132751465,
      "learning_rate": 6e-05,
      "loss": 3.8546,
      "step": 3
    },
    {
      "epoch": 0.0022997316979685703,
      "eval_loss": 0.9854159355163574,
      "eval_runtime": 16.4134,
      "eval_samples_per_second": 33.509,
      "eval_steps_per_second": 16.755,
      "step": 3
    },
    {
      "epoch": 0.0030663089306247606,
      "grad_norm": 2.0427134037017822,
      "learning_rate": 8e-05,
      "loss": 3.7017,
      "step": 4
    },
    {
      "epoch": 0.0038328861632809506,
      "grad_norm": 2.6414690017700195,
      "learning_rate": 0.0001,
      "loss": 4.1406,
      "step": 5
    },
    {
      "epoch": 0.0045994633959371405,
      "grad_norm": 2.220031261444092,
      "learning_rate": 0.00012,
      "loss": 3.3839,
      "step": 6
    },
    {
      "epoch": 0.0045994633959371405,
      "eval_loss": 0.935398280620575,
      "eval_runtime": 16.7375,
      "eval_samples_per_second": 32.86,
      "eval_steps_per_second": 16.43,
      "step": 6
    },
    {
      "epoch": 0.005366040628593331,
      "grad_norm": 2.7698333263397217,
      "learning_rate": 0.00014,
      "loss": 4.302,
      "step": 7
    },
    {
      "epoch": 0.006132617861249521,
      "grad_norm": 3.5623602867126465,
      "learning_rate": 0.00016,
      "loss": 3.4733,
      "step": 8
    },
    {
      "epoch": 0.006899195093905711,
      "grad_norm": 2.596081256866455,
      "learning_rate": 0.00018,
      "loss": 3.3853,
      "step": 9
    },
    {
      "epoch": 0.006899195093905711,
      "eval_loss": 0.7518635988235474,
      "eval_runtime": 16.5706,
      "eval_samples_per_second": 33.191,
      "eval_steps_per_second": 16.596,
      "step": 9
    },
    {
      "epoch": 0.007665772326561901,
      "grad_norm": 2.2372212409973145,
      "learning_rate": 0.0002,
      "loss": 2.4515,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 917953377730560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}